论文标题
图像到图像翻译的2D图像重新构成
2D Image Relighting with Image-to-Image Translation
论文作者
论文摘要
随着生成对抗网络（GAN）的出现，在操纵图像的各种特征方面的控制水平变得更好。这种精细操纵的一个例子是改变了场景中光源的位置。从根本上讲，这是一个不足的问题，因为它需要了解场景几何形状以产生适当的照明效果。这个问题不是一个小问题，如果我们想将光源的方向从任何方向更改为特定方向，可能会变得更加复杂。在这里，我们提供了使用gan解决这个问题的尝试。具体而言，PIX2PIX [ARXIV：1611.07004]接受了数据集VIDIT [ARXIV：2005.05460]训练，其中包含具有不同类型的光温和8种不同光源位置（N，NE，E，E，SE，SE，S，S，S，W，NW，NW）的同一场景的图像。结果是8个神经网络，训练有素，能够将光源的方向从任何方向更改为前面提到的8个方向。此外，我们还提供了一种简单的CNN，该工具训练有素，可以识别图像中光源的方向。
With the advent of Generative Adversarial Networks (GANs), a finer level of control in manipulating various features of an image has become possible. One example of such fine manipulation is changing the position of the light source in a scene. This is fundamentally an ill-posed problem, since it requires understanding the scene geometry to generate proper lighting effects. This problem is not a trivial one and can become even more complicated if we want to change the direction of the light source from any direction to a specific one. Here we provide our attempt to solve this problem using GANs. Specifically, pix2pix [arXiv:1611.07004] trained with the dataset VIDIT [arXiv:2005.05460] which contains images of the same scene with different types of light temperature and 8 different light source positions (N, NE, E, SE, S, SW, W, NW). The results are 8 neural networks trained to be able to change the direction of the light source from any direction to one of the 8 previously mentioned. Additionally, we provide, as a tool, a simple CNN trained to identify the direction of the light source in an image.
